Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comparative descriptions with emotional or judgmental tones

    oai_token-act-pair · gpt-3.5-turbo

    modifiers indicating comparison or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vs
    -0.62
    prints
    -0.58
    atus
    -0.58
     Issa
    -0.56
     Hath
    -0.54
    bryce
    -0.54
    lol
    -0.53
    instead
    -0.53
     Hollow
    -0.53
    ibel
    -0.52
    POSITIVE LOGITS
     consequential
    0.66
    etheless
    0.65
    interstitial
    0.64
    vertising
    0.61
    姫
    0.61
     tempered
    0.59
     mosqu
    0.58
    cffffcc
    0.57
     importantly
    0.56
     adolesc
    0.56
    Act Density 0.525%

    No Known Activations